Skip to main content
Log in

Line-drawing interpretation using probabilistic relaxation

  • Published:
Machine Vision and Applications Aims and scope Submit manuscript

Abstract

This paper shows that probabilistic relaxation is an effective method in the automatic interpretation of line drawings consisting of lines, symbols, and characters, such as electricity distribution diagrams superimposed on maps. The line interpretation problem has been newly formulated as a labeling problem in which probabilistic relaxation is used to obtain globally consistent results. The proposed automatic interpretation method consists of two stages. The first is segmentation and recognition of primitive components, such as symbols, characters, and long lines. The second is long-line interpretation, where probabilistic relaxation is introduced.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. Antoine D, Collin S, Tombre K (1990) Analysis of technical documents: the REDRAW System. PROC, IAPR workshop on structural and syntactic pattern recognition, pp. 192–230

  2. Bunke H (1982) Attributed programmed graph grammars and their application to schematic diagram interpretation. IEEE Trans. PAMI 4, pp. 574–582

    MATH  Google Scholar 

  3. Bunke H (1982) Experience with several methods for the analysis of schematic diagrams. PROC. 6th ICPR, pp. 710–712

  4. Bunke H, Allerman G (1981) Probabilistic relaxation for the interpretation of electrical schematic. PROC, Pattern Recognition and Image Processing, pp. 438–440

  5. Dori D (1988) A syntactic/geometric approach to recognition of dimensions in engineering machine drawings. Computer Vision, Graphics, Image Processing 44:119–138

    Article  Google Scholar 

  6. Ejiri M, Kakumoto S, Miyatake T, Shimada S, Matsushima H (1980) Automatic recognition of design drawings and maps. Image Analysis Applications. New York; Marcel Dekker, pp 73–126

    Google Scholar 

  7. Elliman DG, Lancaster IT (1990) A Review of Segmentation and Contextual Analysis Techniques for Text Recognition. Pattern Recognition 23:337–346

    Article  Google Scholar 

  8. Fahn CS, Wang JF, Lee JY (1988) A Topology-Based Component Extractor for Understanding Electronic Circuit Diagrams. Computer Vision, Graphics, Image Processing, 44:119–138

    Article  Google Scholar 

  9. Gerald M, Tombre K (1990) Discrete Relaxation Applied to Interpretation of Technical Documents. PROC. ICPR, pp. 706–708

  10. Govindan VK, Shivaprasad AP (1990) Character Recognition — a Review. Pattern Recognition 23:671–683

    Article  Google Scholar 

  11. Groen FCA, Sanderson AC, Schlag JF (1985) Symbol Recognition in Electrical Diagrams Using Probabilistic Graph Matching. Pattern Recognition Letters, Vol. 3, pp. 343–350

    Article  Google Scholar 

  12. Hancock ER, Kittler J (1990) Discrete Relaxation. Pattern Recognition 23(7):711–733

    Article  Google Scholar 

  13. Hancock ER, Kittler J (1990) Edge-labelling using dictionary-based relaxation. IEEE PAMI PAMI-12, pp. 165–181

    Google Scholar 

  14. Hori O, Okazaki A (1990) High Quality Vectorization based on a Generic Object Model. PROC, IAPR Workshop on Structural and Syntactic Pattern Recognition, pp. 137–153

  15. Kasturi R, Bow ST, El-Mastri W, Shah J, Gattiker JR, Mokate UB, (1990) A System for Interpretation of Line Drawings. IEEE Trans. PAMI, 12, pp 978–992

    Google Scholar 

  16. Kirkpatrick A, Gelatt CD Jr, Vecchi MP (1983) Optimization by Simulated Annealing. Science 220:671–680

    MathSciNet  Google Scholar 

  17. Maeda A, Shibayama J, Kanechika H, Tanaka S, Shibata M, Wakimoto K (1987) A recognition method for network diagrams. PROC. International Workshop on Machine Vision and Machine Intelligence, pp. 308–213

  18. Okazaki A, Kondo T, Mori K, Tsunekawa S, Kawamoto E (1988) An automatic circuit diagram reader with loop structure-based symbol recognition. IEEE Trans. PAMI, 10(3):331–341

    Google Scholar 

  19. Rammer UE (1972) An iterative procedure for the polygonal approximation. Computer Graphics and Image Processing 1:244–256

    Google Scholar 

  20. Rosenfeld A, Hummenl RA, Zucker SW (1976) Scene Labeling by Relaxation Operations. IEEE Transactions on SMC, SMC-6:420–433

    Google Scholar 

  21. Shimotsuji S (1989) Model-based diagram analysis by generally defined primitives. PROC. 6th Scandinavia Conf. on Image Analysis, pp. 1034–1041

  22. Shimotsuji S (1990) A Robust Drawing Recognition System Based on Contour Shape Analysis. PROC. ICPR, pp. 717–719

  23. Suzuki S, Yamada T (1990) MARIS:MAP RECOGNITION INPUT SYSTEM. Pattern Recognition 23:919–933

    Article  Google Scholar 

  24. Tsujimoto S, Asada H (1991) Resolving Ambiguity in Segmenting Touching Characters. PROC. ICDAR, pp. 701–709

  25. Zucker SW (1976) Relaxation labelling and the reduction of local ambiguities. 3IJCPR, pp. 852–861

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Hori, O., Shimotsuji, S., Hoshino, F. et al. Line-drawing interpretation using probabilistic relaxation. Machine Vis. Apps. 6, 100–109 (1993). https://doi.org/10.1007/BF01211934

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01211934

Key words

Navigation